Copy-paste prompt

Every day at 10am, check our reviews on [Google / Etsy / Amazon / Trustpilot link] for anything new since yesterday. Log each one in [sheet] with the date, stars and main theme, and draft a short, specific reply. For 3 stars or below, offer to continue at [email]. Put the low ratings first. Don't post anything.

Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.

What you need

Browser access to your review pages or a review export
Brand voice notes

How the agent does it

Open each review source and collect reviews newer than the last run.
Score sentiment and pull out the specific complaint or praise.
Draft a short, specific, non-defensive reply; for 1-3 stars, offer a private channel ([email]).
Log every review to a sheet with the date, rating, theme and reply status.

What you get

A review log sheet plus reply drafts. Ratings of 3 stars or below are flagged at the top.

Schedule	Daily at 10am.
Needs your approval	Posting any public reply needs approval.
How to check it worked	Every review in the log has a source URL; no draft mentions facts not in the review or order.

Common mistakes

Public replies that admit fault on legal or safety issues. Escalate those instead of drafting.

Want new jobs like this tested for you? The Agent Operator Club sends members a monthly drop of tested skills (with scripts and sample data), Grok Bot templates and recipes. From $19/month for the first 50 founding members. Join the waitlist.

Setting it up in each agent

In Grok Bot

Ask the Bot to run the prompt once and review the result. Then say "Save the process we just used as a skill called 'Review monitoring and response drafts'" and "Create a routine that runs the Review monitoring and response drafts skill daily at 10am". Grok Bot's docs say a Bot can own up to 50 routines, schedules must be at least five minutes apart, and you should use Test run before you enable one.

In Meta Muse

Paste the prompt into Muse and ask it to remember the job and run it on the schedule. Muse asks for approval before outbound actions and purchases, so keep the 'don't send' line in the prompt. Before you rely on it, check that Muse can reach the apps this recipe needs.

In ChatGPT Dots

Give your dot the prompt as an ongoing goal and set the schedule. Dots can work between chats and ask for approval before sensitive actions. OpenAI says background work counts toward your plan's allowance, so match the frequency to what you actually need.

Run it by hand once with harmless inputs before you schedule it. A test run does real work.